Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Birth

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paranoid
    -0.07
     достаточно
    -0.06
    oen
    -0.06
    olland
    -0.06
    (optional
    -0.06
    argument
    -0.06
    Keeping
    -0.06
     onKeyDown
    -0.06
    úi
    -0.06
    .DockStyle
    -0.06
    POSITIVE LOGITS
     birth
    0.18
     Birth
    0.16
    birth
    0.15
    Birth
    0.15
     births
    0.12
    IRTH
    0.09
    irth
    0.09
    .birth
    0.08
    th
    0.08
     Barth
    0.08
    Act Density 0.008%

    No Known Activations